How to Use the Diese MCP in LlamaIndex

Q: Can LlamaIndex index data from Diese automatically?

Yes. You can write a pipeline that calls listprojecttasks and getprojectdetails, converts the JSON outputs into LlamaIndex Document objects, and upserts them into your vector database.

Index live Diese ERP project data into LlamaIndex vector stores to query your actual business status without hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diese MCP to LlamaIndex

Create your Vinkius account to connect Diese to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Diese with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Diese project logs into searchable knowledge

Stop letting your ERP data sit in a silo. Use this MCP Server to pull active project details through `list_erp_projects` and index them directly into your LlamaIndex document store. Your LlamaIndex agent can then query past project tasks using `list_project_tasks` to answer complex questions about past performance. It combines live Diese data with historical context to give you accurate answers.

Index Diese invoices with this LlamaIndex MCP Server

Reconciling accounts gets easier when your LlamaIndex agent has access to your actual ledger. The agent calls `list_sales_invoices` and `list_business_expenses` to pull raw Diese financial records directly into its context window. By mapping these records against your vectorized internal docs, you can ask LlamaIndex about budget variances. The agent checks actual spend against planned budgets without making up numbers.

Track resource allocations semantically

Use `list_resource_planning` to feed current staff assignments into your LlamaIndex RAG application. This lets you run semantic searches over who is working on what, rather than relying on basic keyword matches. When you need to find who managed a previous task, the agent runs `search_projects_by_name` to find the project, gets the contacts via `list_erp_contacts`, and indexes the relationship for future queries.

Setup guide

Set up Diese MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Diese MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Diese tools.",
)
response = await agent.run("List recent Diese data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Diese. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Diese now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Diese MCP in LlamaIndex

Install llama-index-tools-mcp and set up the BasicMCPClient pointing to your Vinkius URL. Wrap it in McpToolSpec and pass the tools to your LlamaIndex FunctionAgent to start querying.

Yes. You can write a pipeline that calls list_project_tasks and get_project_details, converts the JSON outputs into LlamaIndex Document objects, and upserts them into your vector database.

By using RAG. When you ask about a project, LlamaIndex first runs search_projects_by_name or list_erp_projects to fetch the actual records, forcing the agent to answer using only that retrieved context.

Yes. When initializing the tool spec, you can use the allowed_tools filter to restrict the agent. For example, you can expose list_project_tasks while blocking access to list_sales_invoices.

The raw ERP data remains on your secure Diese servers. LlamaIndex only stores the vectors or text chunks you explicitly choose to index, while Vinkius secures the MCP Server in an isolated runtime.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript